ZigBee indoor positioning system precision parameter study based on BP neural network

With the developing of wireless sensor networks (WSNs), more application approach have greatly encouraged the use of sensors for multi-target tracking. The high efficiency detection and location monitoring are crucial requirements for multi-target tracking in a WSN of indoor environment, especially the situation without the GPS application. In this paper, we proposed an indoor tracking model using Zigbee of IEEE 802.15.4 compliant radio frequency to monitor targets in a special way. Our motivation is to manipulate the erratic or unstable received signal strength indicator (RSSI) signals to deliver the stable and precise position information in the indoor environment. Based on BP neural network methodology, the selective algorithm for WSN parameters A and n values is demonstrated in this paper. An improvement Euclidian distance centroid location algorithm based on statistical uncorrelated vectors to minimize the noise in RSSI values has also been proposed here. Much more experiments about multi-target detection and location to verify the BPNN methodology can effectively improve selecting those A and n parameters in the WSN network. The system architecture, hardware and software organization, as well as the solutions for multiple-targets tracking, RSSI interference and location accuracy have been introduced in details.